Instructions to use junsor/whisper-tiny-aishell with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use junsor/whisper-tiny-aishell with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="junsor/whisper-tiny-aishell")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("junsor/whisper-tiny-aishell") model = AutoModelForSpeechSeq2Seq.from_pretrained("junsor/whisper-tiny-aishell", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from junsor/whisper-tiny-aishell: direct link, hf CLI and curl.
- Browser
- Download file 354 Bytes
-
https://huggingface.co/junsor/whisper-tiny-aishell/resolve/main/adapter_config.json
- Command line
-
hf download hf://junsor/whisper-tiny-aishell/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/junsor/whisper-tiny-aishell/resolve/main/adapter_config.json
354 Bytes
| { | |
| "base_model_name_or_path": "openai/whisper-tiny", | |
| "bias": "none", | |
| "enable_lora": null, | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "lora_alpha": 64, | |
| "lora_dropout": 0.05, | |
| "merge_weights": false, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 32, | |
| "target_modules": [ | |
| "q_proj", | |
| "v_proj" | |
| ], | |
| "task_type": null | |
| } |